bugfix: security & correctness bundle (0.34.1)

Five fixes bundled into one release:

- preserve user-attached tags across crawler upserts
  (repo::crawler::sync_tags now scopes to added_by IS NULL; orphaned
  attachments from deleted users are reaped as crawler-owned)
- gate manga PATCH and cover endpoints on uploaded_by (require_can_edit
  in api::mangas; non-NULL uploaded_by must match the caller)
- equalise login response time across user-existence branches
  (run argon2 against a OnceLock-cached dummy hash on the no-user
  branch so timing doesn't leak username existence)
- crawler download defences (SSRF allowlist of host literals
  including IPv4-mapped IPv6 ranges, 32 MiB streamed size cap,
  reject non-whitelisted image types, three-way chapter-probe
  classifier replaces the binary #avatar_menu check)
- tighten validation and clean up dead unload path
  (attach_tag + create_token enforce 64-char caps; LocalStorage
  rejects NUL bytes explicitly; reader flushFinalProgress drops
  the always-405 sendBeacon path)

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
MechaCat02
2026-05-28 20:24:51 +02:00
parent c5c1179e9d
commit 8d34132883
25 changed files with 1399 additions and 88 deletions

View File

@@ -440,6 +440,170 @@ async fn arbitrary_genres_from_source_get_inserted(pool: PgPool) {
assert_eq!(webtoons_count.0, 1, "case-insensitive lookup reuses the existing row");
}
/// User-attached tags (rows with non-NULL `added_by` in `manga_tags`)
/// must survive a crawler upsert. The crawler owns source-attached tags
/// (added_by IS NULL); user attachments are owned by the user who made
/// them and the recurring metadata pass must not delete them.
#[sqlx::test(migrations = "./migrations")]
async fn sync_tags_preserves_user_attached_tags(pool: PgPool) {
crawler::ensure_source(&pool, "target", "T", "https://x.example")
.await
.unwrap();
let m = sample_manga("foo", "Foo Manga", "hash-1");
let up = crawler::upsert_manga_from_source(&pool, "target", "https://x.example/foo", &m)
.await
.unwrap();
// A real user attaches a personal tag.
let user = mangalord::repo::user::create(&pool, "alice", "phc-stub")
.await
.unwrap();
let outcome = mangalord::repo::tag::attach_to_manga(&pool, up.manga_id, "personal", user.id)
.await
.unwrap();
assert!(outcome.created_attachment);
// Second crawler pass. Use a different metadata_hash so the upsert
// takes the Updated branch, but the bug also fires on Unchanged
// ticks since sync_tags runs unconditionally.
let mut m2 = m.clone();
m2.metadata_hash = "hash-2".into();
m2.tags = vec!["popular".into(), "weekly".into()];
let _ = crawler::upsert_manga_from_source(&pool, "target", "https://x.example/foo", &m2)
.await
.unwrap();
// The user tag must still be attached.
let user_tag_rows: (i64,) = sqlx::query_as(
"SELECT COUNT(*) FROM manga_tags mt \
JOIN tags t ON t.id = mt.tag_id \
WHERE mt.manga_id = $1 AND lower(t.name) = 'personal' \
AND mt.added_by = $2",
)
.bind(up.manga_id)
.bind(user.id)
.fetch_one(&pool)
.await
.unwrap();
assert_eq!(
user_tag_rows.0, 1,
"user-attached tag must survive a crawler upsert"
);
// The source's tags should still attach as well, as crawler-owned.
let source_tag_rows: (i64,) = sqlx::query_as(
"SELECT COUNT(*) FROM manga_tags mt \
JOIN tags t ON t.id = mt.tag_id \
WHERE mt.manga_id = $1 \
AND mt.added_by IS NULL \
AND lower(t.name) IN ('popular', 'weekly')",
)
.bind(up.manga_id)
.fetch_one(&pool)
.await
.unwrap();
assert_eq!(source_tag_rows.0, 2, "source tags re-attach on each pass");
// A subsequent pass where the source drops a previously-seen tag
// must clear that crawler-owned attachment (otherwise crawler-tags
// would only ever accumulate).
let mut m3 = m2.clone();
m3.metadata_hash = "hash-3".into();
m3.tags = vec!["popular".into()];
let _ = crawler::upsert_manga_from_source(&pool, "target", "https://x.example/foo", &m3)
.await
.unwrap();
let weekly_rows: (i64,) = sqlx::query_as(
"SELECT COUNT(*) FROM manga_tags mt \
JOIN tags t ON t.id = mt.tag_id \
WHERE mt.manga_id = $1 AND lower(t.name) = 'weekly'",
)
.bind(up.manga_id)
.fetch_one(&pool)
.await
.unwrap();
assert_eq!(weekly_rows.0, 0, "source-owned tag dropped by source goes away");
// And the user tag still survives that third pass.
let user_tag_rows: (i64,) = sqlx::query_as(
"SELECT COUNT(*) FROM manga_tags mt \
JOIN tags t ON t.id = mt.tag_id \
WHERE mt.manga_id = $1 AND lower(t.name) = 'personal' \
AND mt.added_by = $2",
)
.bind(up.manga_id)
.bind(user.id)
.fetch_one(&pool)
.await
.unwrap();
assert_eq!(user_tag_rows.0, 1);
}
/// `manga_tags.added_by` is `ON DELETE SET NULL` on the user FK. When
/// the attaching user is deleted, their attachments become orphans
/// indistinguishable from crawler-owned rows — and the crawler should
/// reap them on the next pass. Pins the semantic so a future change
/// can't quietly leave orphan rows lying around.
#[sqlx::test(migrations = "./migrations")]
async fn sync_tags_garbage_collects_orphan_user_attachments(pool: PgPool) {
crawler::ensure_source(&pool, "target", "T", "https://x.example")
.await
.unwrap();
let m = sample_manga("foo", "Foo", "hash-1");
let up = crawler::upsert_manga_from_source(&pool, "target", "https://x.example/foo", &m)
.await
.unwrap();
// A user attaches "personal", then the user gets deleted. The
// attachment row stays (manga_tags.manga_id FK is CASCADE on
// mangas only; we never CASCADE-delete user attachments). The FK
// on added_by is `ON DELETE SET NULL`, so the row's owner column
// goes NULL — same shape as a crawler-owned row.
let user = mangalord::repo::user::create(&pool, "bob", "phc-stub")
.await
.unwrap();
let _ = mangalord::repo::tag::attach_to_manga(&pool, up.manga_id, "personal", user.id)
.await
.unwrap();
sqlx::query("DELETE FROM users WHERE id = $1")
.bind(user.id)
.execute(&pool)
.await
.unwrap();
// Sanity: the orphan still exists post-user-delete with added_by NULL.
let (orphan_rows,): (i64,) = sqlx::query_as(
"SELECT COUNT(*) FROM manga_tags mt \
JOIN tags t ON t.id = mt.tag_id \
WHERE mt.manga_id = $1 AND lower(t.name) = 'personal' \
AND mt.added_by IS NULL",
)
.bind(up.manga_id)
.fetch_one(&pool)
.await
.unwrap();
assert_eq!(orphan_rows, 1);
// Next crawler pass — orphan should be reaped along with any
// other source-owned rows that aren't in the new tag list.
let mut m2 = m.clone();
m2.metadata_hash = "hash-2".into();
m2.tags = vec!["popular".into()];
let _ = crawler::upsert_manga_from_source(&pool, "target", "https://x.example/foo", &m2)
.await
.unwrap();
let (orphan_rows,): (i64,) = sqlx::query_as(
"SELECT COUNT(*) FROM manga_tags mt \
JOIN tags t ON t.id = mt.tag_id \
WHERE mt.manga_id = $1 AND lower(t.name) = 'personal'",
)
.bind(up.manga_id)
.fetch_one(&pool)
.await
.unwrap();
assert_eq!(orphan_rows, 0, "orphan user-attached tag should be reaped");
}
#[sqlx::test(migrations = "./migrations")]
async fn re_appearing_manga_clears_dropped_at(pool: PgPool) {
crawler::ensure_source(&pool, "target", "T", "https://x.example")